vit-mlo-512-birads

This model is a fine-tuned version of on the preprocessed1024_config dataset. It achieves the following results on the evaluation set:

• Loss: 1.0864
• Accuracy: {'accuracy': 0.4667085427135678}
• F1: {'f1': 0.3786054240333243}

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
1.103	1.0	796	1.0452	{'accuracy': 0.4748743718592965}	{'f1': 0.21465076660988078}
1.0596	2.0	1592	1.0433	{'accuracy': 0.4748743718592965}	{'f1': 0.21465076660988078}
1.0547	3.0	2388	1.0361	{'accuracy': 0.4748743718592965}	{'f1': 0.21465076660988078}
1.047	4.0	3184	1.0395	{'accuracy': 0.46796482412060303}	{'f1': 0.25128840471066954}
1.0524	5.0	3980	1.0331	{'accuracy': 0.4648241206030151}	{'f1': 0.298317360340153}
1.0268	6.0	4776	1.0224	{'accuracy': 0.47675879396984927}	{'f1': 0.23426509831984135}
1.0043	7.0	5572	1.0609	{'accuracy': 0.417713567839196}	{'f1': 0.3663405670841817}
0.982	8.0	6368	1.0521	{'accuracy': 0.44221105527638194}	{'f1': 0.3650005046420297}
0.9315	9.0	7164	1.0473	{'accuracy': 0.47738693467336685}	{'f1': 0.3727220695970696}
0.9319	10.0	7960	1.0864	{'accuracy': 0.4667085427135678}	{'f1': 0.3786054240333243}

Framework versions

• Transformers 4.20.1
• Pytorch 1.12.0
• Datasets 2.1.0
• Tokenizers 0.12.1